ISSN:2348 9510

International Journal Of Core Engineering & Management(IJCEM)

Volume 1, Issue 2, May 2014

ImageBased Face Detection and Recognition using

MATLAB
Ms. Jaishree Tawaniya, Ms. Rashmi Singh, Ms. Neha Sharma, Mr. Jitendra Patidar
jaishree.tawaniya@gmail.com, rashmi86singh@gmail.com, nehasharma2004@gmail.com,
jitendra_patidar@pies.ac.in

Abstract- Face detection is a computer technology that

determines the locations and sizes of human faces in arbitrary
images. It detects facial features and ignores anything else,
such as buildings, trees and bodies. We have implemented an
efficient system to recognize faces from images with some
near real-time variations. Our approach essentially was to
implement and verify the algorithm. This method consist on
weighting the difference between a given face image and a
mean image, which is obtained by averaging a predefined set
of faces. The training set is a group of face images from which
the mean face is calculated. Face detection takes place by
linearly projecting the image to a low dimensional image
space and weighting the difference with respect to a set of
eigenvectors.

proportions of the face; distance between the eyes, nose,

mouth and jaw; upper outlines of the eye sockets; the sides of
the mouth; location of the nose and eyes; and the area
surrounding the check bones.

Keywords Circular Hough Transform, Covariance matrix,

Eigenvalues, Elliptical Hough Transform, Face segmentation,
Raster
Scan Algorithm.

It is typically used in security systems and can be compared to

other biometrics such as fingerprint or eye iris recognition
systems.

I. INTRODUCTION
Face detection is used in biometrics, often as a part of (or
together with) a facial recognition system. It is also used in
video surveillance, human computer interface and image
database management. Some recent digital cameras use face
detection for auto focus. Face detection can be applied for a
wide variety of problems like image and film processing,
human-computer interaction, criminal identification etc. This
has motivated researchers to develop computational models to
identify the faces, which are relatively simple and easy to
implement. Our goal is to implement the model for a set of
training images and find a mean image of all the images so as
to compute the difference between it and the input image for
proper detection.
Facial recognition is a form of computer vision that uses
faces to identify a person or verify a persons claimed
identity. A facial recognition device is one that views an
image or video of a person and compares it to one that is in
the database. It does this by comparing structure, shape and

Upon enrolment in a facial recognition program, several

pictures are taken of the subject at different angles and with
different facial expressions. At time of verification and
identification the subject stands in front of the camera for a
few seconds, and then the image is compared to those that
have been previously recorded. A facial recognition system is
a computer application for automatically identifying or
verifying a person from a digital image or a video frame from
a video source. One of the ways to do this is by comparing
selected facial features from the image and a facial database.

To prevent a subject from using a picture or mask when being

scanned in a facial recognition program, some security
measures have been put into place. When the user is being
scanned, they may be asked to blink, smile or nod their
head. Another security feature would be the use of
facial thermograph to record the heat in the face.
The main facial recognition methods are:
Feature analysis, neural network, eigenfaces, automatic
face processing.
Some facial recognition software algorithms identify faces by
extracting features from an image of a subject's face.
Other algorithms normalize a gallery of face images and then
compress the face data, only saving the data in the image that
can be used for facial recognition. A probe image is then
compared with the face data.
A fairly new method on the market is three-dimensional facial
recognition. This method uses 3-D sensors to capture
information about the shape of a face. This information is

23

ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014
then used to identify distinctive features on the face, such as
the contour of eye sockets, nose and chin.
The advantages of 3-D facial recognition are that it is not
affected by changes in lighting, and it can identify a face from
a variety of angles, including profile view.
Another new technique in facial recognition uses the visual
details of the skin, as captured in standard digital or scanned
images. This technique is called skin texture analysis, turns
the unique lines, patterns, and spots apparent in a person's skin
into a mathematical space. Preliminary tests have shown that
using skin texture analysis in facial recognition can increase
performance in identification by 20 to 25 percent.
Regardless of specific method used, the facial recognition is
accomplished in a five step process(Step 1) Acquiring the Image of an Individuals Face
2 ways to acquire image
1) Digitally scan an existing photograph
2) Acquire a live picture of a subject
(Step 2) Locate Image of Face
MATLAB (image processing toolbox)is used to locate the
image that has been used.
(Step 3)Analysis of Facial Image
-software measures face according to is peaks and valleys
(nodal points)
-nodal points are used to make a face print

1. Eigenfaces Initialization
Acquire an initial set of face images (the training set)
2. Eigenfaces Algorithm
Calculate the Eigen faces from the training set, keeping only
the M images that correspond to the highest Eigen values.
These M images define the face space. As new faces are
experienced, the Eigen faces can be updated or recalculated
3. Calculate the corresponding distribution in M-dimensional
weight space for each known individual, by projecting their
face images onto the face space.

In this project we will make the program to identify the face

or any image using MATLAB. In this there will be
photographs in our database. Software will check the photo
graph we want to check is in database or not. If not then it will
display image is not in database. If yes then it will display,
image is available in database.
Previous mathematicians have theorized that certain cognitive
processes, such as face recognition, can be emulated through
the use of principal component analysis. we have attempted to
use techniques of principal component analysis, more
specifically, eigen-vector analysis, to develop a computer
program capable of face recognition. Specifically, the goal of
our project was to investigate a mathematical basis and model
for face recognition using principal component analysis with
eigenvectors, and then implement a working model in the
form of a computer program.
The fundamental idea behind principal component analysis
with eigenvectors has its basis in linear algebra. Put simply, if
there are a series of multi-dimensional vectors representing
objects which have similarities, it is possible to use a
transformation matrix and eigenvectors to orient a space
which requires fewer dimensions to accurately describe these
multidimensional vectors.

(Step 4) Comparison
-the face print created by the software is compared to all face
prints the system has stored in its database.
(Step 5)-Match Or No Match
-software decides whether or not any comparisons from step 4
are close enough to declare a possible match
FACE RECOGNITION TECHNOLOGY WITH EIGEN
VALUES

For instance, if in three dimensional space, there was a cloud

of particles that lied in a two dimensional plane skewed from
the axes (Fig 1), it would be possible to orient a new space
with a new origin and new unit vectors such that the cloud
which previously required a three dimensional representation
could now easily be represented in only two dimensions.
FLOW DIAGRAM

Insert data
base image

Training
set
Give path

24

ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014

Normalized
the training set

be determined as a unknown face. If the input image is above

these two thresholds, the image is determined NOT to be a
face.

Taking
mean image
Getting
eigen faces

4. If the image is found to be an unknown face, you could

decide whether or not you want to add the image to your
training set for future recognitions. You would have to repeat
steps 1 trough 7 to incorporate this new face image.

Giving
input

TWO MAIN USES

1) IDENTFICATION
-figure out Who is X?
-accomplished by system performing a one-to-many search

image
STEPS
1. The first step is to obtain a set S with M face images. Each
image is transformed into a vector of size N and placed into
the set.
2. After you have obtained your set, you will obtain the mean
image
3. Then you will find the difference between the input
image and the mean image
4. Next we seek a set of M ortho normal vectors, un, which
best describes the distribution of the data. The kth vector, uk, is
chosen such that is a maximum, subject to
Note: uk and k are the eigenvectors and eigenvalues of
the covariance matrix C
We obtain the covariance matrix C in the following manner
5. AT
6. Now we have to find the eigenvectors, vl, ul

2) VERIFICATION
-answer the question Is this X?
-accomplished by the system performing a one-to-one
search

BENEFITS
The benefits of facial recognition are that it is not intrusive,
can be done from a distance even without the user being
aware they are being scanned. (i.e.: bank or government
office)
What sets apart facial recognition from other biometric
techniques is that it can be used for surveillance purposes; as
in searching for wanted criminals, suspected terrorists, and
missing children. Facial recognition can be done from far
away so with no contact with the subject so they are unaware
they are being scanned.
Facial recognition is most beneficial to use for facial
authentication than for identification purposes, as it is too easy
RECOGNITION PROCEDURE
for someone to alter their face, features with a disguise or
1. A new face is transformed into its Eigen face components.
mask, etc. Environment is also a consideration as well as
First we compare our input image with our mean image and
subject motion and focus on the camera.
multiply their difference with each eigenvector of the L matrix. Facial recognition, when used in combination with another
Each value would represent a weight and would be saved on a
biometric method, can improve verification and identification
vector .
results dramatically.
2. We now determine which face class provides the best
description for the input image. This is done by minimizing
the Euclidean distance
3. The input face is considered to belong to a class if k is
bellow an established threshold . Then the face image is
considered to be a known face. If the difference is above the
given threshold, but bellow a second threshold, the image can

APPLICATION DOMAIN
As one of the most successful applications of image analysis
and understanding, face recognition has recently gained
significant attention image analysis and understanding face
especially during the past several years. There are at least two
reasons for such a trend: the first is the wide range
of commercial and law enforcement applications and the
second is the availability of feasible technologies after 35

25

ISSN:2348 9510
International Journal Of Core Engineering & Management(IJCEM)
Volume 1, Issue 2, May 2014
years of research. Moreover recent significant advances in
multimedia processing have also helped to advance the
applications of face recognition technology. Among the
diverse contents of multimedia face objects are particularly
important for e.g.- database software capable of searching for
ace objects or a particular face object is very useful.
Another example is a security system that is able to
automatically track human objects and report their
IDs.Though tracking and recognizing face objects is a routine
task for humans building such system is still an active
research. Among many proposed face recognition
Schemes image based approaches are possibly the most
promising ones. However the 2D images/patterns of 3D face
objects can dramatically change due to lighting and viewing
variations. Hence, illumination and pose problems present
significant
Obstacles for wide applications of this type of approaches. In
this we review existing methods extensively. And then we
propose using a generic 3D model to enhance existing system.
More specifically we use the 3D model to synthesize the socalled prototype image from a given image acquired under
different lighting and viewing condition. The advantages of
this approach are computational simplicity and system
robustness which are essential for any real applications.

Some other attempts at facial recognition by machine have

allowed for little or no variability in these quantities. Yet the
method of correlation (or pattern matching) of unprocessed
optical data, which is often used by some researchers, is
certain to fail
CONCLUSION
In 2006, the performance of the latest face recognition
algorithms was evaluated in the Face Recognition Grand
Challenge (FRGC). High-resolution face images, 3-D face
scans, and iris images were used in the tests. The results
indicated that the new algorithms are 10 times more accurate
than the face recognition algorithms of 2002 and 100 times
more accurate than those of 1995. Some of the algorithms
were able to outperform human participants in recognizing
faces and could uniquely identify identical twins.

Low-resolution images of faces can be enhanced using face

hallucination. Further improvements in high resolution, mega
pixel cameras in the last few years have helped to resolve the
issue of insufficient resolution.
This recognition problem is made difficult by the great
variability in head rotation and tilt, lighting intensity and angle,
facial expression, aging, etc. in cases where the variability is
great. In particular, the correlation is very low between two
pictures of the same person with two different head rotations.
In this paper we discussed an efficient and accurate method or
human face identification and segmentation in gray scale
images. This method utilizes the inherently elliptical nature of
the human head and fits an ellipse to the head. The resultant
information about the ellipse is then used to mask out
unwanted feature points in the recognition phase of the
identification system. When compared to other methods, the
proposed hybrid method has the advantage of
eigenvaluesapproach, CHT and Raster Scan Algorithm. It
does not use the tangent of edge points to extract the ellipses
and avoids false alarms. The amount of data required for
ellipse detection and parameters estimation using the proposed
method is minimal, since it uses only eigenvalues of
covariance matrix. When compared to the conventional face
space methods, the main strengths of our method are its less
computational time, low memory requirements and accuracy
of face detection and segmentation.. The proposed method
was tested on images with uniform background, cluttered and
noisy
Conditions.

REFERENCES
[1] http://www.face-rec.org/databases/
[2] Matthew A. Turk and Alex P. Pentland. Face
recognition using eigenfaces.
[3] www.mathworks.com
[4] :
http://www.intechopen.com/books/show/title/face_
recognition

26